Object classfication from RGB-D images using depth context kernel descriptors

TY - GEN

T1 - Object classfication from RGB-D images using depth context kernel descriptors

AU - Pan, Hong

AU - Olsen, Søren Ingvor

AU - Zhu, Yaping

PY - 2015/12/9

Y1 - 2015/12/9

N2 - Context cue is important in object classification. By embedding the depth context cue of image attributes into kernel descriptors, we propose a new set of depth image descriptors called depth context kernel descriptors (DCKD) for RGB-D based object classification. The motivation of DCKD is to use the depth consistency of image attributes defined within a neighboring region to improve the robustness of descriptor matching in the kernel space. Moreover, a novel joint spatial-depth pooling (JSDP) scheme, which further partitions image sub-regions using the depth cue and pools features in both 2D image plane and the depth direction, is developed to take full advantage of the available depth information. By embedding DCKD and JSDP into the standard object classification pipeline, we achieve superior performance to state-of-the-art methods on RGB-D benchmarks for object classification and scene recognition.

AB - Context cue is important in object classification. By embedding the depth context cue of image attributes into kernel descriptors, we propose a new set of depth image descriptors called depth context kernel descriptors (DCKD) for RGB-D based object classification. The motivation of DCKD is to use the depth consistency of image attributes defined within a neighboring region to improve the robustness of descriptor matching in the kernel space. Moreover, a novel joint spatial-depth pooling (JSDP) scheme, which further partitions image sub-regions using the depth cue and pools features in both 2D image plane and the depth direction, is developed to take full advantage of the available depth information. By embedding DCKD and JSDP into the standard object classification pipeline, we achieve superior performance to state-of-the-art methods on RGB-D benchmarks for object classification and scene recognition.

KW - Faculty of Science

KW - RGB-D object classification, Context cue,

U2 - 10.1109/ICIP.2015.7350851

DO - 10.1109/ICIP.2015.7350851

M3 - Article in proceedings

SP - 512

EP - 516

BT - 2015 IEEE International Conference on Image Processing (ICIP 2015)

PB - IEEE

T2 - International Conference on Image Processing 2015

Y2 - 27 September 2015 through 30 September 2015

ER -